arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2111.05628cs.CRcs.AIcs.CY
收藏

可信研究环境(TRE)中的机器学习模型泄露、挑战和机遇

Machine Learning Models Disclosure from Trusted Research Environments (TRE), Challenges and Opportunities

University of Dundee(邓迪大学);NHS National Services Scotland(苏格兰NHS国家服务局);University of the West of England(西英格兰大学)

Esma Mansouri-Benssassi, Simon Rogers, Jim Smith, Felix Ritchie, Emily Jefferson

摘要:

近年来,人工智能(AI)在医疗保健和医学领域的应用越来越多。为了实现对个人数据的访问,可信研究环境(TREs)提供了安全可靠的环境,研究人员可以在其中访问敏感的个人数据并开发人工智能(AI)和机器学习模型。然而,目前很少有TREs支持使用机器学习的自动化基于AI的建模。在文献中已经进行了早期的尝试,从设计的角度提出和介绍隐私保护机器学习[1]。然而,在处理模型披露方面,对贸易效率报告的实际决策指导存在差距。具体地,机器学习的使用产生了公开来自TRE的新类型的输出的需要,诸如经训练的机器学习模型。尽管TREs对统计输出的披露有明确的政策,但对经过训练的模型在发布后可能泄露个人训练数据的程度还不清楚,TREs中也没有安全披露这些模型的指导方针。在本文中,我们介绍了从TREs中公开训练好的机器学习模型的挑战。我们首先概述了一般的机器学习模型,并描述了它们在医疗保健和医学中的一些应用。我们定义了一般训练机器学习模型的主要漏洞。我们还描述了影响披露机器学习模型的漏洞的主要因素。本文还提供了一些见解和分析方法,可以在TREs中引入这些方法,以减轻在披露训练模型时隐私泄露的风险。

英文摘要:

Artificial intelligence (AI) applications in healthcare and medicine have increased in recent years. To enable access to personal data, Trusted Research environments (TREs) provide safe and secure environments in which researchers can access sensitive personal data and develop Artificial Intelligence (AI) and Machine Learning models. However currently few TREs support the use of automated AI-based modelling using Machine Learning. Early attempts have been made in the literature to present and introduce privacy preserving machine learning from the design point of view [1]. However, there exists a gap in the practical decision-making guidance for TREs in handling models disclosure. Specifically, the use of machine learning creates a need to disclose new types of outputs from TREs, such as trained machine learning models. Although TREs have clear policies for the disclosure of statistical outputs, the extent to which trained models can leak personal training data once released is not well understood and guidelines do not exist within TREs for the safe disclosure of these models. In this paper we introduce the challenge of disclosing trained machine learning models from TREs. We first give an overview of machine learning models in general and describe some of their applications in healthcare and medicine. We define the main vulnerabilities of trained machine learning models in general. We also describe the main factors affecting the vulnerabilities of disclosing machine learning models. This paper also provides insights and analyses methods that could be introduced within TREs to mitigate the risk of privacy breaches when disclosing trained models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑